Structural response estimation method based on particle swarm optimisation/support vector machine and response correlation characteristics

AbstractExisting systems for diagnosing heart diseases are time consuming, expensive, and error prone. Aiming at this, a detection algorithm for factors inducing heart diseases based on a particle swarm optimisation-support vector machine (PSO-SVM) optimised by association rules (ARs) was proposed. Firstly, AR was used to select features from a disease data set so as to train feature sets. Then, PSO-SVM was used to classify training and testing sets, and then the factors inducing heart diseases were analysed. Finally, the effectiveness and reliability of the proposed algorithm was verified by experiments on the UCI Cleveland data set with confidence as the index. The experimental results showed that females have less risk of having a heart attack than males. Irrespective of gender, once diagnosed with chest pain without symptoms and angina caused by exercise, people are more likely to suffer from heart disease. Moreover, compared with another two advanced classification algorithms, the proposed algorithm showed better classification performance and therefore can be used as a powerful tool to help doctors diagnose and treat heart diseases.

Download Full-text

On-Line Estimation Method of Lithium-Ion Battery Health Status Based on PSO-SVM

Frontiers in Energy Research ◽

10.3389/fenrg.2021.693249 ◽

2021 ◽

Vol 9 ◽

Author(s):

Ran Li ◽

Wenrui Li ◽

Haonian Zhang ◽

Yongqin Zhou ◽

Weilong Tian

Keyword(s):

Support Vector Machine ◽

Estimation Method ◽

Particle Swarm ◽

Lithium Ion ◽

State Of Charge ◽

Joint Estimation ◽

Support Vector ◽

Particle Swarm Algorithm ◽

Battery Management System ◽

Safe Driving

Battery management system (BMS) refers to a critical electronic control unit in the power battery system of electric vehicles. It is capable of detecting and estimating battery status online, especially estimating state of charge (SOC) and state of health (SOH) accurately. Safe driving and battery life optimization are of high significance. As indicated from recent literature reports, most relevant studies on battery health estimation are offline estimation, and several problems emerged (e.g., long time-consuming, considerable calculation and unable to estimate online). Given this, the present study proposes an online estimation method of lithium-ion health based on particle swarm support vector machine algorithm. By exploiting the data of National Aeronautics and Space Administration (NASA) battery samples, this study explores the changing law of battery state of charge under different battery health. In addition, particle swarm algorithm is adopted to optimize the kernel function of the support vector machine for the joint estimation of battery SOC and SOH. As indicated from the tests (e.g., Dynamic Stress Test), it exhibits good adaptability and feasibility. This study also provides a certain reference for the application of BMS system in electric vehicle battery online detection and state estimation.

Download Full-text